rainremove

这款小DEMO是关于自己学习LOD地形分层算法的例子，其中简单显示了实现算法的过程(The DEMO is a small study on their own examples of LOD terrain hierarchical algorithm, which simply shows the process of algorithm)

Packet matching code.

对监控视频中的目标进行识别，提取背景信息(The target in the surveillance video is identified and background information is extracted)

说明：  DensePose用深度学习把2D图像坐标映射到3D人体表面上，再加上以每秒多帧的速度处理密集坐标，最后实现动态人物的精确定位和姿态估计。该技术集目标检测、姿态估计、目标部分/实例分割等多种计算机视觉任务于一身的一个综合问题。(DensePost maps 2D image coordinates to 3D human body surface by in-depth learning, and processes dense coordinates at the speed of multiple frames per second. Finally, it realizes precise positioning and attitude estimation of dynamic characters. This technology integrates many kinds of computer vision tasks, such as target detection, attitude estimation, target part/instance segmentation, etc.)

背景差分法，用于视频，该程序可直接运行。(Background differential method, used in video, can run directly.)

影像内定向程序编写，便于实习航摄影像的内定向(Orientation within the image programming, easy to practice within the aviation photography as directed)

冈萨雷斯数字图像处理MATLAB版，是我们学习图像处理必备的书籍(Gonzales digital image processing MATLAB version, we study the image processing necessary books)

matlab的GUI设计教程，希望对利用matlab设计GUI的用户带来一定的帮助(Matlab GUI design tutorial, I hope the use of MATLAB design GUI users to bring some help)

首先将非平稳的故障振动信号进行双树复小波包分解，得 到不同频带的分量；然后对每个分量求其峭度值和相关系数并进行比较；最后选取峭度值和相关系数较大的分量 进行软阈值降噪和双树复小波包重构，即可有效地消除振动信号中噪声的干扰，同时保留信号中的有效信息即实 现了故障特征信息的提取。(In view of the above situation, a new fault diagnosis method is proposed based on dual-tree complex wavelet packet transform and threshold de-noising. Firstly, the non-stationary fault signal is decomposed into several different frequency band components through dual-tree complex wavelet packet decomposition. Secondly, Kurtosis and the cross-correlation coefficient of each component are obtained and compared. Due to the kurtosis reflecting the signal variations, if the kurtosis value is bigger, the degree of the change of signal is bigger too. The correlation coefficient can reflect the proximity between the component and the original signal at the same time, the correlation coefficient is bigger, the more similar with the original signal. Finally, the components that have a bigger value are chosen to be de-noised by a soft threshold and reconstructed by dual-tree complex wavelet packet transform. The noise interference was eliminated effectively, and the effective si)

说明：  窗口界面使用KAYA SDK连接采集卡相机获取采集图像(use KAYA sdk connect with grabber and capture image data)